# Self-Evolution Knowledge Distillation for LLM-based Machine Translation

arXiv: https://arxiv.org/abs/2412.15303 · HTML: https://mlsanity.com/paper/2412.15303/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 19 Dec 2024.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023)
- [Large language models effectively leverage document-level context for literary translation, but critical errors persist](https://mlsanity.com/paper/2304.03245/) (2023)
- [Extrapolating Large Language Models to Non-English by Aligning Languages](https://mlsanity.com/paper/2308.04948/) (2023)
- [Selective Knowledge Distillation for Neural Machine Translation](https://mlsanity.com/paper/2105.12967/) (2021)
- [Revisiting Knowledge Distillation for Autoregressive Language Models](https://mlsanity.com/paper/2402.11890/) (2024)
- [Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation](https://mlsanity.com/paper/2206.06067/) (2022)
- [PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning](https://mlsanity.com/paper/2402.12842/) (2024)
- [Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE](https://mlsanity.com/paper/2212.01853/) (2022)
- [On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation](https://mlsanity.com/paper/2209.03316/) (2022)
- [On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation](https://mlsanity.com/paper/2110.01811/) (2021)
- [Self-Evolution Learning for Discriminative Language Model Pretraining](https://mlsanity.com/paper/2305.15275/) (2023)
- [Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks](https://mlsanity.com/paper/2305.13547/) (2023)
- [Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning](https://mlsanity.com/paper/2403.14399/) (2024)

## Built on by (most cited first, 1 of 1)

- [Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages](https://mlsanity.com/paper/2507.21568/) (2025)

## Abstract (arXiv)

Knowledge distillation (KD) has shown great promise in transferring knowledge from larger teacher models to smaller student models. However, existing KD strategies for large language models often minimize output distributions between student and teacher models indiscriminately for each token. This overlooks the imbalanced nature of tokens and their varying transfer difficulties. In response, we propose a distillation strategy called Self-Evolution KD. The core of this approach involves dynamically integrating teacher distribution and one-hot distribution of ground truth into the student distribution as prior knowledge, which promotes the distillation process. It adjusts the ratio of prior knowledge based on token learning difficulty, fully leveraging the teacher model's potential. Experimental results show our method brings an average improvement of approximately 1.4 SacreBLEU points across four translation directions in the WMT22 test sets. Further analysis indicates that the improvement comes from better knowledge transfer from teachers, confirming our hypothesis.